Pdf Solutions, Incorporated

Qing Zhu

Richard Gene Burch

Tomonori Honda

Jeffrey Drue David

Lin Lee Cheong

Michael Keleher

Jonathan Holt

Dennis Ciplickas

John Kibarian

Brian E Stine

Kenneth Harris

Said Akar

Keith Arnold

Vaishnavi Reddipalli

A template for assigning the most probable root causes for wafer defects. The bin map data for a subject wafer can be compared with bin map data for prior wafers to find wafers with similar issues. A probability can be determined as to whether the same root cause should be applied to the subject wafer, and if so, the wafer can be labeled with that root cause accordingly.

Wafer bin map based root cause analysis

A sequence of models accumulates r-squared values for an increasing number of variables in order to quantify the importance of each variable to the prediction of a targeted yield or parametric response.

Machine learning variable selection and root cause discovery by cumulative prediction

Classifying wafers using Collaborative Learning. An initial wafer classification is determined by a rule-based model. A predicted wafer classification is determined by a machine learning model. Multiple users can manually review the classifications to confirm or modify, or to add user classifications. All of the classifications are input to the machine learning model to continuously update its scheme for detection and classification.

Collaborative learning model for semiconductor applications

A semiconductor image classifier. Convolution functions are applied to modify the wafer images in order to extract key information about the image. The modified images are condensed then processed through a series of pairwise classifiers, each classifier configured to determine that the image is more like one of the pair than the other. Probabilities from each classifier are collected to form a prediction for each image.

Abnormal wafer image classification

A machine learning model for each die for imputing process control parameters at the die. The model is based on wafer sort parametric measurements at multiple test sites across the entire wafer, as well as yield results for the wafer. This allows for a better analysis of outlier spatial patterns leading to improved yield results.

Die level product modeling without die level input data

Enhancement of less dominant patterns for parametric wafer measurements. Dominant patterns are removed from the parametric pattern thereby revealing a less dominant pattern. The less dominant patterns can be used to identify root causes for yield loss that are not visible in the original parametric measurements.

Pattern-enhanced spatial correlation of test structures to die level responses

Scheme for detection and classification of semiconductor equipment faults. Sensor traces are monitored and processed to separate known abnormal operating conditions from unknown abnormal operating conditions. Feature engineering permits focus on relevant traces for a targeted feature. A machine learning model is built to detect and classify based on an initial classification set of anomalies. The machine learning model is continuously updated as more traces are processed and learned.

Anomalous equipment trace detection and classification

Semiconductor yield is modeled at the die level to predict die that are susceptible to early lifetime failure (ELF). A first die yield calculation is made from parametric data obtained from wafer testing in a semiconductor manufacturing process. A second die yield calculation is made from die location only. The difference between the first die yield calculation and the second die yield calculation is a prediction delta. Based on an evaluation of the first die yield calculation and the prediction delta, the likelihood of early lifetime failure can be identified and an acceptable level of die loss can be established to remove die from further processing.

Growing community of inventors

Rowlett, TX, United States of America

Qing Zhu